Signals are classified by deterministic rules and carry provenance-based confidence. Each item links to its original source.
As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical priority. However, whether LLMs exhibit consistent value preferences across languages remains underexplored, par…
Large language models have collapsed the cost of producing lexically elaborate prose, and whether peer reviewers still reward it is a question about the evaluator, not about the text. When the association between a writing cue and review scores moves across y…
Training capable cyber agents is often treated primarily as a problem of model scale, yet open-weight post-training is constrained more directly by the cost of executable environments, reliable multi-turn supervision, and access to strong teachers. We present…
In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qwen3-Embedding and Qwen3-VL-Embedding. We find that removing prefix states is substantially more damaging in…
Large Language Models demonstrate remarkable proficiency in static reasoning, yet training them as autonomous agents through Reinforcement Learning (RL) for long-horizon tasks is often hindered by severe reward sparsity. While conventional \textit{agent-side…
Aligned language models fail under two independent pressures: the structural jailbreak class recently formalized as Involuntary In-Context Learning (IICL), which reframes a harmful request as the final missing cell of a data-labeling task completed by pattern…
We present Miles v0.1, a full-stack, production-ready system for frontier post-training. Building upon the clean design of slime, Miles designs each stage of the reinforcement-learning (RL) training loop around a single principle: components should be verifie…
In molecular discovery, molecule size is coupled to composition, structure, and other target properties. Yet most 3D generators require molecule size to be specified before generation. Here, we introduce Equivariant-Free Transformer-Autoencoded Latent Flow Ma…
Multilingual LLMs show stereotype-related behavior that varies across languages, but behavioral scores do not show where the relevant information is represented or how it affects the output. To investigate these internal mechanisms, we compare linear probing,…
We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for intelligence. E…
Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute editing techniques. Professional editing depends on shot structure, transition grammar, audio-video cut relat…
Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consist…
Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate training convergence and enhance sampling quality, yet the…
Modern industrial ads ranking stacks are increasingly bottlenecked not by model capacity or training compute, but by the throughput of human ML iteration - the cycles of research, implementation, training, debugging, evaluation, and launch required to surface…
Automatic safety judges -- systems such as Llama Guard or a GPT-4o grading prompt that decide whether a model's reply is harmful -- produce the numbers behind almost every reported jailbreak success rate, defense evaluation, and safety leaderboard. We ask whe…
Modern LLM agents increasingly rely on reusable skills, yet as skill libraries scale to thousands of entries, effective retrieval becomes a bottleneck. Graph-of-Skills (GoS) addresses this challenge by exploiting dependency-aware graph structure for scalable…
Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions they make. We argue these are co-symptoms of one structural deficiency in the d…
Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing traditional linear scalarization to experience severe metric oscillations. To address optimization conflict…
Sparse autoencoder (SAE)-based steering has been widely used to address knowledge conflicts by guiding LLMs to be more faithful to the contextual knowledge. Existing methods usually perform mass steering, which modifies a large batch of SAE features identifie…
Full-duplex speech models require training data that preserves turn-taking, overlap, interruption, and backchannel behavior, yet these signals are entangled across speakers in noisy real-world recordings. We present Conversational Voice, a pipeline that conve…
We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how scheming arises from the interaction of key factors, such as instrumental goals, environmental affordances, oversight conditions, and perceived c…
Large language model (LLM) agents are increasingly employed for offensive cybersecurity tasks such as automated vulnerability discovery, reconnaissance, and penetration testing. This new capability also threatens one of the defender's most valuable tools: dec…
Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in scene reconstruction, computational photography, and robotics, among others. Despite the field's maturity, recent models still struggle to ge…
Firms making inventory decisions have access to operational data, optimization tools, and large language models (LLMs). Typically, data characterize the operating environment, optimization selects parameters within a prespecified inventory policy class, and L…
The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing defenses such as GitHub Dependabot often raise many false alerts because their coarse-grained matching cannot d…